© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 156896
    Prev
    Next
    INDEX
    Explanations

    time, files, while, volume, Had, arches, refunds, positions

    np_acts-logits-general · gemini-2.5-flash-lite

    tokens after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     можем
    0.58
     у
    0.55
     мате
    0.55
     aujourd
    0.54
    й
    0.54
    ،
    0.54
     provare
    0.52
     өл
    0.52
     легко
    0.52
     природ
    0.52
    POSITIVE LOGITS
    同时也
    0.46
    print
    0.46
    -
    0.44
    িজ
    0.42
    bird
    0.42
    kil
    0.41
    關於
    0.40
     daisy
    0.40
    about
    0.40
     sibling
    0.40
    Activations Density 0.001%

    No Known Activations